Pith. sign in

REVIEW 4 major objections 4 minor 12 references

This paper introduces ACME, a dataset of robot and pedestrian motion gathered at eight sites in five countries with seven robot platforms, and argues that it captures more challenging and more culturally varied social-navigation scenarios t

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-01 06:11 UTC pith:G7U6XV7Q

load-bearing objection ACME is a genuinely large, well-organized multi-country social-navigation dataset that deserves serious referee time, but its headline 'more challenging' and cross-cultural claims need homography validation and error bars before they carry full weight. the 4 major comments →

arxiv 2607.21964 v1 pith:G7U6XV7Q submitted 2026-07-24 cs.RO cs.AI

ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Dataset

Shashank Rao Marpally , Allan Wang , Atharva Ghotavadekar , Renato Alexandre Ribeiro , Nhat Le , Pilar Bachiller-Burgos , Pranav Goyal , Subham Agrawal
show 30 more authors
Yasuhiro Nitta Howard Ziyu Han Daeun Song Masaki Kuribayashi Kohei Uehara Xiyue Wang Yangzhe Kong Duc M. Nguyen Amirreza Payandeh Gerardo P\'erez-Gonz\'alez Alejandro Torrej\'on-Harto Jeeho Ahn Tisha Jain Andrew Stratton Elvin Yang Jorge de Heuvel Nico Ostermann-Myrau Sai Anudeep Sajja Mithilya Raj Daisuke Sato Gaston Rouquette Nikolas Martelaro Maki Sugimoto Hironobu Takagi Chieko Asakawa Maren Bennewitz Aaron Steinfeld Xuesu Xiao Christoforos Mavrogiannis Harold Soh
This is my paper
classification cs.RO cs.AI
keywords social navigationpedestrian trajectory predictionmulti-cultural datasetmulti-embodiment robot databird's-eye view trackinghuman-verified annotationsrobot speechbenchmarking
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

ACME is a large-scale collection of real-world robot navigation and pedestrian movement data, assembled by eight teams in five countries using seven different robot bodies. The paper's central claim is that this is the largest and most diverse human-demonstrated dataset of its kind: 29.35 hours of onboard robot sensor data and 43.5 hours of overhead, human-verified pedestrian trajectories. Its purpose is to give social-navigation researchers data that includes cultural and morphological variation, which prior single-site datasets lack, so that robots can learn context-appropriate behavior rather than a narrow, location-specific norm. The paper also shows that state-of-the-art navigation and trajectory-prediction models perform noticeably worse on ACME than on older benchmarks, which it interprets as evidence that ACME contains harder, more realistic scenarios. If that is right, ACME becomes a benchmark for testing whether models generalize across cultures, environments, and robot forms.

Core claim

On its own terms, the paper's discovery is that a coordinated multi-site collection effort can produce a social-navigation dataset with broader cultural and morphological coverage than prior efforts, and that this breadth changes what models see. ACME robot trajectories are shorter and more goal-directed than earlier in-the-wild datasets; scenes are more socially constrained, with pedestrians closer to the robot; and off-the-shelf planners fail more often per meter. Pedestrian tracks show large variance in speed, density, and duration, and measurable cross-country differences in passing side and personal space (right-side passing in US and German data, left-side tendencies in Singapore and J

What carries the argument

The central object is the dataset itself: synchronized multi-modal onboard recordings (odometry, egocentric RGB, 3D LiDAR, and timestamped robot speech in some subsets) plus overhead bird's-eye-view (BEV) cameras whose pedestrian tracks are converted from pixel coordinates to ground-plane metric coordinates via homography matrices. That conversion is the load-bearing mechanism for the cross-cultural trajectory analysis, turning overhead video into quantitative distances, speeds, and passing-side measurements. A second mechanism is the annotation pipeline: automated tracking followed by human verification at 10 Hz, with tools to relabel, add, break, join, and disentangle tracks, which support

Load-bearing premise

The paper's own section on transforming BEV images to ground plane acknowledges 'the inherent inaccuracies of tag-based homography estimation'; that calibration accuracy, turning overhead camera pixels into ground-plane meters, is the load-bearing premise for the metric-space trajectory statistics and cross-cultural comparisons.

What would settle it

Place surveyed ground-truth markers at each collection site, project them through the published homographies, and compare to their measured positions; if typical errors exceed roughly half a meter, the metric-space trajectory statistics and cross-cultural comparisons would not be trustworthy.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Trajectory-prediction models trained on long-standing benchmarks lose about 0.1 m ADE and 0.15 m FDE when evaluated on ACME, and more when only moving pedestrians are considered, making ACME a harder generalization benchmark.
  • Off-the-shelf geometric planners fail two to four times more often per minute or per meter on ACME than on earlier social-navigation datasets, making ACME useful for stress-testing planners in socially constrained scenes.
  • The dataset's scenario tags (narrow corridors, blind corners, crowds, queues, overtaking) let researchers filter for specific situations, so policies can be trained or evaluated on the long tail of social navigation rather than on averaged behavior.
  • Robot speech annotations tied to pedestrian density and traversability provide a first real-world resource for learning when a robot should speak to negotiate space, not just how it should move.
  • Because trajectories are grounded in metric coordinates and verified by humans, the dataset can support quantitative study of how walking speed, passing side, and personal space vary by country and environment layout.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • A direct test the paper does not run: if ACME delivers the diversity it claims, a navigation policy trained on a subset of its countries should transfer to a held-out country better than a policy trained on a single country; that experiment would separate the value of data volume from the value of cultural coverage.
  • The passing-side results imply that 'socially compliant' navigation has no single ground truth; deployed robots may need to infer or adapt to local conventions, which points toward learning algorithms that condition on geography or context rather than a universal policy.
  • The heavy presence of static and slow pedestrians in ACME suggests that trajectory predictors should model intent (standing, conversing, queueing) explicitly; the paper's dynamic-only benchmark hints at this, but the dataset's semantic tags make a stronger intent-aware training setup possible than the paper explores.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

4 major / 4 minor

Summary. The paper introduces ACME, a social-navigation and pedestrian-trajectory dataset collected by 8 teams at 8 sites in 5 countries using 7 robot embodiments. It comprises 29.35 hours of onboard robot data (odometry, RGB, LiDAR, and, for some subsets, robot speech) and 43.5 hours of overhead BEV pedestrian data, with 72.1K human-verified pedestrian trajectories provided in pixel and metric coordinates. The authors compare ACME with SCAND and MuSoHu on pedestrian density, traversability, and planner failure rates; benchmark vision-navigation models (ViNT, NoMAD) and trajectory-prediction models (SocialGAN, AgentFormer, SGNet, TUTR, MoFlow); and use the BEV data to analyze cross-cultural differences in walking speed, passing side, and personal space. The headline claims are that ACME is the largest and most diverse human-demonstrated social-navigation and trajectory-prediction dataset and that it captures more challenging scenarios and a broader distribution of pedestrian behavior than prior datasets.

Significance. If the claims hold, ACME would be a substantial community resource. Its strengths include multi-country and multi-embodiment coverage, a large human-verified BEV trajectory set with metric coordinates, scenario and semantic tags, robot-speech annotations, and a reproducible-style pipeline with open-sourced annotation tools and processing scripts. The paper also provides initial benchmarks for both navigation and trajectory-prediction models, which can serve as baselines for future work. The multi-site IRB/ethics documentation is a positive example for dataset papers. The main risk is that the quantitative value of the dataset depends on unvalidated homography and synchronization procedures, and the 'more challenging' claim relies on proxy metrics whose definitions are not fully specified. These issues are fixable and should be addressed before publication.

major comments (4)
  1. [Transformation from BEV Image Plane to Ground Plane] Metric-space trajectories are a central contribution, and they feed the cross-cultural analyses (Figs. 17-18) and the trajectory-prediction benchmark (Table 6). However, the paper provides no quantitative validation of the BEV-to-ground homographies. The text acknowledges 'the inherent inaccuracies of tag-based homography estimation' and later limits trajectories to within ±25 m of the poster tag, but no reprojection-error statistics, ground-truth comparisons, or distance-dependent sensitivity analyses are reported. In addition, the Miraikan/Keio synchronization uses manual frame selection (Appendix), whose temporal error is not quantified. Please report per-site reprojection RMSE and validate on surveyed points, and show that coordinate errors are small relative to the reported effects: ADE/FDE gaps of 0.1-0.38 m in Table 6 and personal-space differences of roughly 0.5-1 m in Fig. 18. W
  2. [Comparison to a Geometric Planner (Fig. 13)] The claim that ACME is 'more challenging' than SCAND and MuSoHu relies heavily on the TEB planner failure rates shown in Fig. 13. However, the manuscript never defines what counts as a planner failure, reports raw failure counts, or provides confidence intervals. The statement that 'the primary mode of planner failure is the presence of pedestrians at the sampled goal position' is asserted but not substantiated with quantitative evidence. Because the comparison across datasets depends on local planner parameters, costmap configuration, and the failure criterion, these details are load-bearing. Please state the failure definition (e.g., no plan within timeout, oscillation, collision), report counts and rates per dataset, and include a sensitivity analysis with respect to planner settings.
  3. [Traversability analysis (Fig. 10)] The traversability metric is computed with 'a finetuned SAM2 model,' but the manuscript does not describe how that model was trained, what data it was trained on, how the traversability mask is defined, or how accurate its predictions are on the egocentric images of SCAND, MuSoHu, and ACME. The cited reference (Wang et al. 2024b) appears to be a navigation system rather than the segmentation model used. Since this proxy feeds Fig. 10(d)-(g) and the robot-speech analysis in Fig. 12, please document the model and validate its outputs on a manually annotated sample from each dataset, or otherwise present the traversability results as illustrative rather than as a basis for the 'more challenging' claim.
  4. [Comparison across Datasets (Figs. 17-18)] The passing-side and personal-space analyses are presented as evidence that ACME captures cross-cultural behavioral differences, but no confidence intervals, sample sizes per direction bin, or statistical tests are reported. The observed left/right preferences and personal-space differences could be influenced by per-site homography errors, within-tag variation in corridor widths, or small interaction counts in some direction bins. The paper already hedges that 'lateral differences should not be attributed too strongly to culture,' but the figures and surrounding text nevertheless draw directional conclusions. Please provide uncertainty quantification and, where appropriate, statistical tests, or explicitly frame these results as descriptive observations.
minor comments (4)
  1. [Data Accessibility Statement] The data accessibility statement says the dataset is shared 'via a password-protected Box in the following link:' but the link appears to be empty in the manuscript. Please include the URL, or at minimum a clear description of how reviewers can access the data.
  2. [Traversability section] The term 'finetuned SAM2' is ambiguous. Please clarify whether this refers to the SAM2 segmentation model or to a traversability model from the cited Wang et al. (2024b) work, and add the appropriate citation.
  3. [Fig. 15 and Table 5] The standard-deviation values are reported as '±' numbers without being defined in the caption or text. Please state explicitly that these are standard deviations, and consider adding the number of trajectories per sub-dataset in Fig. 15.
  4. [Abstract] The abstract refers to 'A Cross-cultural' dataset while the title uses 'Multi-Cultural.' Please standardize the terminology across the paper.

Circularity Check

0 steps flagged

No significant circularity; central dataset claims rest on independent collection, statistics, and external benchmarks.

full rationale

The paper's central claims are that ACME is the largest/diverse social-navigation and trajectory-prediction dataset and that it captures more challenging scenarios and a broader distribution of pedestrian behavior. These claims are supported by independent evidence: duration/trajectory counts in Table 5; scenario-complexity metrics computed with external off-the-shelf detectors (ByteTrack, SAM2) and the TEB planner applied uniformly to ACME, SCAND, and MuSoHu; trajectory-prediction benchmarks using models trained on ETH/UCY and evaluated on ACME; and behavioral statistics derived from the annotated metric trajectories. No fitted parameter is renamed as a prediction, and no equation reduces a claimed result to its own input by construction. The acknowledged homography inaccuracy ('we acknowledge the inherent inaccuracies of tag-based homography estimation') is a measurement-error/validity concern, not circularity: the homographies come from AprilTags or surveyed keypoints, not from the pedestrian trajectories they transform. Similarly, QR-code or manual-frame temporal synchronization is a data-quality limitation, not a circular step. Self-citations with overlapping authors exist (e.g., TBD, Bi3, Raj et al., Mavrogiannis et al. 2023), but they are used for methodology inspiration, prior-work context, or as comparison baselines; none is load-bearing for the size, diversity, or challenge claims. The 'more challenging' conclusion from planner failure rates is an external, in-principle falsifiable measurement. The paper also explicitly cautions that FPV-space quantities 'should not be interpreted as direct metric measurements,' showing awareness of limits. Overall, the derivation chain is self-contained relative to the paper's fitted values, and the central claims have independent content; only minor non-load-bearing self-citation keeps the score above zero.

Axiom & Free-Parameter Ledger

7 free parameters · 5 axioms · 0 invented entities

The dataset does not introduce a theory or model; its central claims are empirical. The parameters listed are hand-set thresholds in the post-processing and analysis pipeline. The axioms are the measurement and annotation assumptions that the dataset's validity rests on.

free parameters (7)
  • Interaction distance threshold = 4 m
    Used to define pedestrian interaction points in passing-side and personal-space analyses (Section 'Comparison across Datasets'). Choice affects all interaction counts and distance averages.
  • Dynamic pedestrian speed threshold = 0.5 m/s
    Defines moving vs. static pedestrians in trajectory prediction benchmarks and speed analyses (Table 6, 'Comparison across Datasets').
  • Minimum trajectory duration = 3.2 s
    Trajectories shorter than 3.2s are discarded in metric post-processing (Section 'BEV Camera Data').
  • Trajectory smoothing window = 5
    Smoothing window size applied to metric trajectories (Section 'BEV Camera Data').
  • Jump fix velocity threshold = 5 m/s
    Instantaneous velocities above 5 m/s treated as tracking noise and linearly interpolated (Section 'BEV Camera Data').
  • Ground-plane bounding box = ±25 m
    Pedestrian positions limited to ±25m around marker to avoid inaccurate far-field projections (Section 'BEV Camera Data').
  • BEV sampling rate for predictions = 2.5 Hz
    Trajectories downsampled to ETH/UCY-compatible 2.5Hz for benchmark.
axioms (5)
  • domain assumption Homography estimation via AprilTags/keypoints yields accurate ground-plane projection
    Load-bearing for all metric trajectory analyses; acknowledged inaccuracies in 'Transformation from BEV Image Plane to Ground Plane'.
  • domain assumption SAM2 traversability and YOLO/ByteTrack pedestrian detection are reliable proxies for scene complexity
    Used for density/traversability comparisons (Fig 10). The paper notes these are model-based, not direct measurements.
  • domain assumption TEB planner failures measure scenario challenge
    Comparison to geometric planner uses TEB failure rates as proxy for social-complexity (Fig 13).
  • domain assumption Human verification of ByteTrack trajectories yields ground-truth pedestrian positions
    Annotation tool relies on human corrections; quality depends on annotator diligence (Section 'Pedestrian Trajectory Tracking and Correction').
  • domain assumption Cultural inferences are justified by five countries and site selection
    Cross-cultural comparisons treat country as a variable while acknowledging environmental confounds.

pith-pipeline@v1.3.0-alltime-deepseek · 27819 in / 9787 out tokens · 94006 ms · 2026-08-01T06:11:12.209253+00:00 · methodology

0 comments
read the original abstract

Understanding how robots and humans move in shared spaces is essential for designing effective social robot navigation policies and predicting human behavior. However, existing datasets often lack the diversity needed to capture differences in culture, geography, and human-robot interaction-factors that strongly shape appropriate social behavior. To address this gap, we introduce ACME: A Cross-cultural, Multi-Embodiment dataset for social navigation. A large-scale data collection effort across 8 sites in 5 countries, using 7 robot embodiments, ACME is a large and diverse multi-modal dataset aimed at advancing social navigation research, providing 29.35 hours of onboard robot data and 43.5 hours of overhead pedestrian tracking data. Unlike prior datasets, it focuses on capturing goal-driven social navigation behavior in complex social scenarios with explicit robot-crowd interaction through robot speech. To facilitate learning navigation policies and predicting pedestrian trajectories, ACME provides 3D and 2D scene features, odometry, interaction information, and human-annotated pedestrian trajectory labels. We make ACME easy to use by providing both human-readable data for each sensor modality as well as raw binary data. Our qualitative and quantitative analyses show that our dataset captures more challenging scenarios and a broader distribution of pedestrian behavior than previous datasets.

Figures

Figures reproduced from arXiv: 2607.21964 by Aaron Steinfeld, Alejandro Torrej\'on-Harto, Allan Wang, Amirreza Payandeh, Andrew Stratton, Atharva Ghotavadekar, Chieko Asakawa, Christoforos Mavrogiannis, Daeun Song, Daisuke Sato, Duc M. Nguyen, Elvin Yang, Gaston Rouquette, Gerardo P\'erez-Gonz\'alez, Harold Soh, Hironobu Takagi, Howard Ziyu Han, Jeeho Ahn, Jorge de Heuvel, Kohei Uehara, Maki Sugimoto, Maren Bennewitz, Masaki Kuribayashi, Mithilya Raj, Nhat Le, Nico Ostermann-Myrau, Nikolas Martelaro, Pilar Bachiller-Burgos, Pranav Goyal, Renato Alexandre Ribeiro, Sai Anudeep Sajja, Shashank Rao Marpally, Subham Agrawal, Tisha Jain, Xiyue Wang, Xuesu Xiao, Yangzhe Kong, Yasuhiro Nitta.

Figure 1
Figure 1. Figure 1: ACME comprises of data collected by 8 teams across 5 countries on 7 embodiments across diverse crowd scenarios. has proposed an evaluation infrastructure for socially compliant navigation, ranging from canonical scenario protocols (Pirk et al. 2022) to comprehensive guidelines spanning metrics, benchmarks, and datasets (Francis et al. 2025). Yet, as critically surveyed by (Mavrogiannis et al. 2023), fundam… view at source ↗
Figure 2
Figure 2. Figure 2: Teleoperation interface used to collect data in NUS where the teleoperator can relay robot speech commands and mark start and end of trajectory segments during data collection. BEGIN END BEGIN DISCARD BEGIN END Trajectory 1 Trajectory 2 Trajectory 3 Accepted Discarded Accepted [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Data filtering with Event Markings is capped by the limited size and variety of existing datasets, they revealed that a comprehensive human motion dataset may enable additional supervised research approaches to social navigation. The ACME Dataset In this section, we describe the methodology and nature of the data captured in ACME* . An overview of the data duration, hardware, sensors, and locations for eac… view at source ↗
Figure 4
Figure 4. Figure 4: Compared to prior Social Navigation Datasets that collect unconstrained long trajectories, ACME trajectories are more localized and goal-oriented. teleoperator guidelines for maximizing the utility of the dataset and capturing natural human-robot-interactions in the wild: • Stay as far away from the robot as safely possible: To emulate “Wizard of Oz” conditions, teleoperators are advised to stay away from … view at source ↗
Figure 5
Figure 5. Figure 5: Position Synchronization with April Tags. The tag is visible to both the robot (suitcase) and the BEV camera. errors. Instead, we first obtained the robot’s pose with respect to the ground plane-based world frame at the time when it sees the upright tag. We then estimated the BEV cameras’ poses in the world frame via tag detection at the synchronized time from both the robot and the BEV cameras. Homographi… view at source ↗
Figure 6
Figure 6. Figure 6: Different types of Data Anonymization across ACME specified by the IRB requirements for each institution. In order to retain the lost information, pedestrian tracking information used to anonymize the data (bounding box, segmentation mask, and keypoints) is provided [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Application interface for human verification process. It contains a media player and multiple options to correct tracking errors manually. (at 4Hz) in index.extension format to ease accessing cross-modality data with time synchronization. For each trajectory, the following data streams are available, provided in separate files/folders: • Odometry: Provided in the form of CSV files containing 10 headers cor… view at source ↗
Figure 8
Figure 8. Figure 8: Distribution of Scenarios captured by ACME. Scenarios dependent on the type of location where the robot and pedestrians navigate are Location-specific scenario tags while those characterized by the type of relative motion between the pedestrians and the robot are Pedestrian-centric Scenario Tags [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Example BEV tags overlaid on top of pedestrian trajectories. Each color represents a different semantic tag. The yellow areas are open spaces, the blue areas are wide corridors, the red areas are narrow corridors, the green areas are intersection areas, and the orange areas are blind corner areas. The colored lines show the annotated trajectories in the corresponding recording session. characterization of … view at source ↗
Figure 10
Figure 10. Figure 10: Pedestrian density and traversability analysis of scenes captured from egocentric view across ACME and 2 recent Social navigation datasets: SCAND (Karnan et al. 2022a) and MuSoHu (Nguyen et al. 2023). Robot Speech Trajectories collected in NUS, UEx, Miraikan, and Keio also contain annotations of robot speech usage, indicating when and where robot speech was used during crowd navigation. We discovered that… view at source ↗
Figure 11
Figure 11. Figure 11: Navigation scenarios from ACME with the same number of detected pedestrians but presenting vast differences in the navigation challenge faced. (a) Scenes with Robot speech utterances in NUS data (b) Scenes with Robot speech utterances in UEx data (c) Scenes with speech utterances in Miraikan & Keio data [PITH_FULL_IMAGE:figures/full_fig_p011_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Robot speech usage in the NUS, UEx, Miraikan, and Keio subsets. Each marker corresponds to a frame in which a robot speech utterance was issued, plotted by pedestrian density and traversability at that timestamp. Gray contour lines show the overall distribution of pedestrian density and traversability within the corresponding data subset. • “Excuse Me/Please Give Way”: When the robot’s path was hindered b… view at source ↗
Figure 13
Figure 13. Figure 13: Although the distribution of Hausdorff distances between the expert trajectory and TEB remains similar across datasets, the higher planner failure rates showcase that off-the-shelf planners have more difficulty navigating in the scenes captured in ACME compared to other datasets. planners would be deemed socially noncompliant. We perform an analysis identical to that of Raj et al. (2024), by sampling futu… view at source ↗
Figure 14
Figure 14. Figure 14: Qualitative Results: Trajectories generated by SoTA foundational navigation models compared with the ground truth trajectories [PITH_FULL_IMAGE:figures/full_fig_p013_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Trajectory statistics of our data compared to prior datasets with ± standard deviation. The statistics on the right side of the dashed lines are data for each of our sub-datasets. (a) duration in seconds. (b) average motion speed in meters per second. (c) minimum distance between any two pedestrians over time in meters. combined dataset, consistent with the findings from their respective papers. The newer… view at source ↗
Figure 16
Figure 16. Figure 16: Mean, median, and speed distribution of all trajectory segments capped at 5m/s. Only trajectories with average speed > 0.5m/s are included. The top yellow cluster data are from sub-datasets with significant open area data. The middle blue cluster data are from sub-datasets that contain significant wide corridor data. The bottom red cluster data are from sub-datasets that contain significant narrow corrido… view at source ↗
Figure 17
Figure 17. Figure 17: Relative direction of pedestrians when interacting with each other. Interaction is defined when two pedestrians get to the closest point to each other, and their distance is < 4m. The top yellow cluster data are from sub-datasets with significant open area data. The middle blue cluster data are from sub-datasets that contain significant wide corridor data. The bottom red cluster data are from sub-datasets… view at source ↗
Figure 18
Figure 18. Figure 18: Personal space, or average minimum distance of pedestrians when interacting with each other. Interaction is defined when two pedestrians get to the closest point to each other and their distance is < 4m. The top yellow cluster data are from sub-datasets with significant open area data. The middle blue cluster data are from sub-datasets that contain significant wide corridor data. The bottom red cluster da… view at source ↗
Figure 19
Figure 19. Figure 19: Time Synchronization with timestamp embedded QR Codes Time-Synchronization between BEV and onboard data In order to time-synchronize the BEV camera feed with the on-board robot data, we used a QR-code-based method, which allowed post-hoc temporal syncing of the two data streams. This accommodated the use of commercial BEV cameras with limited SDKs (where direct integration with our ROS-based setup was inf… view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

12 extracted references · 2 linked inside Pith

  1. [1]

    Agrawal S, Ostermann-Myrau N, Dengler N and Bennewitz M (2026) Peroi: A pedestrian-robot interaction dataset for learning avoidance, neutrality, and attraction behaviors in social navigation. In:Proc. of IEEE International Conference on Robotics and Automation (ICRA). Alahi A, Goel K, Ramanathan V , Robicquet A, Fei-Fei L and Savarese S (2016a) Social lst...

    2026

  2. [7]

    3153–3160

    IEEE, pp. 3153–3160. Olson E (2011) Apriltag: A robust and flexible visual fiducial system. In:2011 IEEE international conference on robotics and automation. IEEE, pp. 3400–3407. Paez-Granados D, He Y , Gonon D, Jia D, Leibe B, Suzuki K and Billard A (2022a) Pedestrian-robot interactions on autonomous crowd navigation: Reactive control methods and evaluat...

    arXiv 2011

  3. [38]

    pp. 474–482. Chen YF, Liu M, Everett M and How JP (2017) Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. In:2017 IEEE international conference on robotics and automation (ICRA). IEEE, pp. 285–

    2017

  4. [292]

    De Heuvel J, Corral N, Kreis B, Conradi J, Driemel A and Bennewitz M (2023) Learning depth vision-based personalized robot navigation from dynamic demonstrations in virtual reality

    Cheng AC, Ji Y , Yang Z, Gongye Z, Zou X, Kautz J, Bıyık E, Yin H, Liu S and Wang X (2024) Navila: Legged robot vision-language-action model for navigation.arXiv preprint arXiv:2412.04453. De Heuvel J, Corral N, Kreis B, Conradi J, Driemel A and Bennewitz M (2023) Learning depth vision-based personalized robot navigation from dynamic demonstrations in vir...

    Pith/arXiv arXiv 2024

  5. [803]

    Van Den Berg J, Snape J, Guy SJ and Manocha D (2011) Reciprocal collision avoidance with acceleration-velocity obstacles

    Trautman P, Ma J, Murray RM and Krause A (2015) Robot navigation in dense human crowds: Statistical models and experimental studies of human–robot cooperation.The International Journal of Robotics Research34(3): 335–356. Van Den Berg J, Snape J, Guy SJ and Manocha D (2011) Reciprocal collision avoidance with acceleration-velocity obstacles. In:2011 IEEE I...

    arXiv 2015

  6. [864]

    ACM Transactions on Human-Robot Interaction14(2)

    Francis A, P ´erez-D’Arpino C, Li C, Xia F, Alahi A, Alami R, Bera A, Biswas A, Biswas J, Chandra R, Chiang HTL, Everett M, Ha S, Hart J, How JP, Karnan H, Lee TWE, Manso LJ, Mirsky R, Pirk S, Singamaneni PT, Stone P, Taylor A V , Trautman P, Tsoi N, V ´azquez M, Xiao X, Xu P, Yokoyama N, Toshev A and Mart ´ın-Mart´ın R (2025) Principles and guidelines fo...

    arXiv 2025

  7. [1572]

    Sorokowska A, Sorokowski P, Hilpert P, Cantarero K, Frackowiak T, Ahmadi K, Alghraibeh AM, Aryeetey R, Bertoni A, Bettache K et al

    Song D, Liang J, Payandeh A, Raj AH, Xiao X and Manocha D (2024) Vlm-social-nav: Socially aware robot navigation through scoring using vision-language models.IEEE Robotics and Automation Letters. Sorokowska A, Sorokowski P, Hilpert P, Cantarero K, Frackowiak T, Ahmadi K, Alghraibeh AM, Aryeetey R, Bertoni A, Bettache K et al. (2017) Preferred interpersona...

    2024

  8. [2011]

    3457–3464

    IEEE, pp. 3457–3464. Bradwell HL, Winnington R, Thill S and Jones RB (2021) Morphology of socially assistive robots for health and social care: A reflection on 24 months of research with anthropomorphic, zoomorphic and mechanomorphic devices. In:2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN). IEEE, pp. 376–383....

    2021

  9. [2016]

    ISBN 978-3-319-46484-8, pp. 549–565. R¨osmann C, Hoffmann F and Bertram T (2017) Integrated online trajectory planning and optimization in distinctive topologies. Robotics and Autonomous Systems88: 142–153. Rudenko A, Kucner TP, Swaminathan CS, Chadalavada RT, Arras KO and Lilienthal AJ (2020a) Th ¨or: Human-robot navigation data collection and accurate m...

    Pith/arXiv arXiv 2017

  10. [2022]

    ISBN 978- 3-031-20047-2, pp

    Cham: Springer Nature Switzerland. ISBN 978- 3-031-20047-2, pp. 1–21. Zhou B, Wang X and Tang X (2012) Understanding collective crowd behaviors: Learning a mixture model of dynamic pedestrian-agents. In:2012 IEEE Conf. on Comput. Vis. and Pattern Recognit.IEEE, pp. 2871–2878. Zhu Y , Yang SM, Magnusson M and Wang A (2026) Hicrowd: Hierarchical crowd flow ...

    2012

  11. [2026]

    18699 67.2 2D trajectory from bird’s eye camera Teleop 3 Outdoor Bi3 (Stratton et al. 2026a) 185 630 Motion Capture System, RGB Camera, Depth Camera Autonomous 2 Indoor ACME 3013 1761 3D-LiDAR, RGB(D) Camera, Overhead BEV Cameras, Odometry Human operated, Teleop 7 Both Prepared usingsagej.cls 24 Journal Title XX(X) Appendix Miscellaneous Details Data Cura...

    2021

  12. [4282]

    In:2018 IEEE/RSJ international conference on intelligent robots and systems (IROS)

    Hirose N, Sadeghian A, V ´azquez M, Goebel P and Savarese S (2018) Gonet: A semi-supervised deep learning approach for traversability estimation. In:2018 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp. 3044–3051. Hirose N, Shah D, Sridhar A and Levine S (2023) Sacson: Scalable autonomous control for social navigation....

    arXiv 2018